Method and system for providing speech recognition
AssigneeMCI, Inc.
InventorDavid Sannerud
Life of this patent
Estimating the term…
Abstract
An approach for providing speech recognition is disclosed. A name is retrieved from a user based on data provided by the user. The user is prompted for a name of the user. A first audio input is received from the user in response to the prompt. Speech recognition is applied to the first audio input using a name grammar database to output a recognized name. A determination is made whether the recognized name matches the retrieved name. If no match is determined, the user is re-prompted for the name of the user for a second audio input. Speech recognition is applied to the second audio input using a confidence database having entries less than the name grammar database.
Claims24
A method, comprising:
- retrieving a name from a user based on data provided by the user;
- prompting the user for a name of the user;
- receiving a first audio input from the user in response to the prompt;
- applying speech recognition to the first audio input using a name grammar database to output a recognized name;
- determining whether the recognized name matches the retrieved name;
- re-prompting the user for the name of the user, if no match is determined;
- receiving a second audio input from the user in response to the re-prompt;
- and
- applying speech recognition to the second audio input using a confidence database having entries less than the name grammar database.
An apparatus, comprising:
- a speech recognition logic configured to receive a first audio input from a user, wherein the first audio input represents an uttered name provided by the user in response to a prompt, wherein a retrieved name of the user is previously retrieved based on data provided by the user, the speech recognition logic being further configured to apply speech recognition to the first audio input using a name grammar database to output a recognized name, and to determine whether the recognized name matches the retrieved name,
- wherein the user is re-prompted for an uttered name of the user for a second audio input, if no match is determined, the speech recognition logic further applying speech recognition to the second audio input using a confidence database having entries less than the name grammar database.
A system, comprising:
- a voice response unit configured to retrieve a name from a user based on data provided by the user, and to prompt the user for a name of the user;
- and
- a speech recognition logic configured to receive a first audio input from the user in response to the prompt, and to apply speech recognition to the first audio input using a name grammar database to output a recognized name, the speech recognition logic being further configured to determine whether the recognized name matches the retrieved name,
- wherein the voice response unit is further configured to re-prompt the user for the name of the user for a second audio input, if no match is determined,
- wherein the speech recognition logic is further configured to apply speech recognition to the second audio input using a confidence database having entries less than the name grammar database.
Dependencies are inferred from the claim text.